Towards Data-Driven Adaptive Exoskeleton Assistance for Post-stroke Gait

TL;DR

This paper develops a data-driven approach using a multi-task TCN to estimate ankle torque for adaptive exoskeleton assistance in post-stroke gait, demonstrating real-time feasibility with a prototype.

Contribution

It introduces a novel multi-task TCN model trained on post-stroke data, enabling real-time ankle torque estimation for adaptive exoskeleton control in post-stroke patients.

Findings

Model achieved $R^2$ of 0.74 on post-stroke data.

Demonstrated real-time sensing, estimation, and actuation with a prototype.

Pretrained on healthy data to improve post-stroke torque estimation.

Abstract

Recent work has shown that exoskeletons controlled through data-driven methods can dynamically adapt assistance to various tasks for healthy young adults. However, applying these methods to populations with neuromotor gait deficits, such as post-stroke hemiparesis, is challenging. This is due not only to high population heterogeneity and gait variability but also to a lack of post-stroke gait datasets to train accurate models. Despite these challenges, data-driven methods offer a promising avenue for control, potentially allowing exoskeletons to function safely and effectively in unstructured community settings. This work presents a first step towards enabling adaptive plantarflexion and dorsiflexion assistance from data-driven torque estimation during post-stroke walking. We trained a multi-task Temporal Convolutional Network (TCN) using collected data from four post-stroke participants walking on a treadmill ($R^2$ of $0.74 \pm 0.13$). The model uses data from three inertial measurement units (IMU) and was pretrained on healthy walking data from 6 participants. We implemented a wearable prototype for our ankle torque estimation approach for exoskeleton control and demonstrated the viability of real-time sensing, estimation, and actuation with one post-stroke participant.